arco-mini-run-4 / checkpoint-2250 /trainer_state.json
appvoid's picture
Upload folder using huggingface_hub
99e4837 verified
{
"best_metric": null,
"best_model_checkpoint": null,
"epoch": 1.0,
"eval_steps": 5000,
"global_step": 2250,
"is_hyper_param_search": false,
"is_local_process_zero": true,
"is_world_process_zero": true,
"log_history": [
{
"epoch": 0.0044444444444444444,
"grad_norm": 0.5433621406555176,
"learning_rate": 2.0000000000000003e-06,
"loss": 1.9321,
"step": 10
},
{
"epoch": 0.008888888888888889,
"grad_norm": 0.561606764793396,
"learning_rate": 4.000000000000001e-06,
"loss": 1.6473,
"step": 20
},
{
"epoch": 0.013333333333333334,
"grad_norm": 0.5591593384742737,
"learning_rate": 6e-06,
"loss": 1.6608,
"step": 30
},
{
"epoch": 0.017777777777777778,
"grad_norm": 0.4737153649330139,
"learning_rate": 8.000000000000001e-06,
"loss": 1.593,
"step": 40
},
{
"epoch": 0.022222222222222223,
"grad_norm": 0.49554353952407837,
"learning_rate": 1e-05,
"loss": 1.5977,
"step": 50
},
{
"epoch": 0.02666666666666667,
"grad_norm": 0.5209193229675293,
"learning_rate": 1.2e-05,
"loss": 1.7224,
"step": 60
},
{
"epoch": 0.03111111111111111,
"grad_norm": 0.6041632294654846,
"learning_rate": 1.4000000000000001e-05,
"loss": 1.7147,
"step": 70
},
{
"epoch": 0.035555555555555556,
"grad_norm": 0.5665949583053589,
"learning_rate": 1.6000000000000003e-05,
"loss": 1.8407,
"step": 80
},
{
"epoch": 0.04,
"grad_norm": 0.46845224499702454,
"learning_rate": 1.8e-05,
"loss": 1.7081,
"step": 90
},
{
"epoch": 0.044444444444444446,
"grad_norm": 0.5971758365631104,
"learning_rate": 2e-05,
"loss": 1.6679,
"step": 100
},
{
"epoch": 0.04888888888888889,
"grad_norm": 0.5474440455436707,
"learning_rate": 2.2000000000000003e-05,
"loss": 1.7097,
"step": 110
},
{
"epoch": 0.05333333333333334,
"grad_norm": 0.5440825819969177,
"learning_rate": 2.4e-05,
"loss": 1.699,
"step": 120
},
{
"epoch": 0.057777777777777775,
"grad_norm": 0.5594825148582458,
"learning_rate": 2.6000000000000002e-05,
"loss": 1.5727,
"step": 130
},
{
"epoch": 0.06222222222222222,
"grad_norm": 0.5222841501235962,
"learning_rate": 2.8000000000000003e-05,
"loss": 1.7716,
"step": 140
},
{
"epoch": 0.06666666666666667,
"grad_norm": 0.5387088060379028,
"learning_rate": 3e-05,
"loss": 1.7168,
"step": 150
},
{
"epoch": 0.07111111111111111,
"grad_norm": 0.582731306552887,
"learning_rate": 3.2000000000000005e-05,
"loss": 1.6742,
"step": 160
},
{
"epoch": 0.07555555555555556,
"grad_norm": 0.4863213002681732,
"learning_rate": 3.4000000000000007e-05,
"loss": 1.8133,
"step": 170
},
{
"epoch": 0.08,
"grad_norm": 0.558056652545929,
"learning_rate": 3.6e-05,
"loss": 1.6343,
"step": 180
},
{
"epoch": 0.08444444444444445,
"grad_norm": 0.5111934542655945,
"learning_rate": 3.8e-05,
"loss": 1.7636,
"step": 190
},
{
"epoch": 0.08888888888888889,
"grad_norm": 0.5395738482475281,
"learning_rate": 4e-05,
"loss": 1.802,
"step": 200
},
{
"epoch": 0.09333333333333334,
"grad_norm": 0.5868604779243469,
"learning_rate": 4.2e-05,
"loss": 1.7807,
"step": 210
},
{
"epoch": 0.09777777777777778,
"grad_norm": 0.6610602140426636,
"learning_rate": 4.4000000000000006e-05,
"loss": 1.7328,
"step": 220
},
{
"epoch": 0.10222222222222223,
"grad_norm": 0.4879331588745117,
"learning_rate": 4.600000000000001e-05,
"loss": 1.6453,
"step": 230
},
{
"epoch": 0.10666666666666667,
"grad_norm": 0.49884936213493347,
"learning_rate": 4.8e-05,
"loss": 1.7553,
"step": 240
},
{
"epoch": 0.1111111111111111,
"grad_norm": 0.5518313050270081,
"learning_rate": 5e-05,
"loss": 1.7899,
"step": 250
},
{
"epoch": 0.11555555555555555,
"grad_norm": 0.4758407473564148,
"learning_rate": 5.2000000000000004e-05,
"loss": 1.8008,
"step": 260
},
{
"epoch": 0.12,
"grad_norm": 0.6643330454826355,
"learning_rate": 5.4000000000000005e-05,
"loss": 1.8044,
"step": 270
},
{
"epoch": 0.12444444444444444,
"grad_norm": 0.6399062275886536,
"learning_rate": 5.6000000000000006e-05,
"loss": 1.707,
"step": 280
},
{
"epoch": 0.1288888888888889,
"grad_norm": 0.5865938663482666,
"learning_rate": 5.8e-05,
"loss": 1.8816,
"step": 290
},
{
"epoch": 0.13333333333333333,
"grad_norm": 0.696479320526123,
"learning_rate": 6e-05,
"loss": 1.8446,
"step": 300
},
{
"epoch": 0.13777777777777778,
"grad_norm": 0.5724856853485107,
"learning_rate": 6.2e-05,
"loss": 1.8147,
"step": 310
},
{
"epoch": 0.14222222222222222,
"grad_norm": 0.61114901304245,
"learning_rate": 6.400000000000001e-05,
"loss": 1.7069,
"step": 320
},
{
"epoch": 0.14666666666666667,
"grad_norm": 0.47783616185188293,
"learning_rate": 6.6e-05,
"loss": 1.945,
"step": 330
},
{
"epoch": 0.1511111111111111,
"grad_norm": 0.5438987612724304,
"learning_rate": 6.800000000000001e-05,
"loss": 1.8745,
"step": 340
},
{
"epoch": 0.15555555555555556,
"grad_norm": 0.6080267429351807,
"learning_rate": 7e-05,
"loss": 1.7863,
"step": 350
},
{
"epoch": 0.16,
"grad_norm": 0.5038191676139832,
"learning_rate": 7.2e-05,
"loss": 1.7838,
"step": 360
},
{
"epoch": 0.16444444444444445,
"grad_norm": 0.6252524256706238,
"learning_rate": 7.4e-05,
"loss": 1.7028,
"step": 370
},
{
"epoch": 0.1688888888888889,
"grad_norm": 0.5980324149131775,
"learning_rate": 7.6e-05,
"loss": 1.7397,
"step": 380
},
{
"epoch": 0.17333333333333334,
"grad_norm": 0.7241755723953247,
"learning_rate": 7.800000000000001e-05,
"loss": 1.7465,
"step": 390
},
{
"epoch": 0.17777777777777778,
"grad_norm": 0.5854328870773315,
"learning_rate": 8e-05,
"loss": 1.7453,
"step": 400
},
{
"epoch": 0.18222222222222223,
"grad_norm": 0.6349270939826965,
"learning_rate": 8.2e-05,
"loss": 1.6712,
"step": 410
},
{
"epoch": 0.18666666666666668,
"grad_norm": 0.6904433965682983,
"learning_rate": 8.4e-05,
"loss": 1.7417,
"step": 420
},
{
"epoch": 0.19111111111111112,
"grad_norm": 0.5410600900650024,
"learning_rate": 8.6e-05,
"loss": 1.8458,
"step": 430
},
{
"epoch": 0.19555555555555557,
"grad_norm": 0.6205611228942871,
"learning_rate": 8.800000000000001e-05,
"loss": 1.7107,
"step": 440
},
{
"epoch": 0.2,
"grad_norm": 0.5386173129081726,
"learning_rate": 9e-05,
"loss": 1.8438,
"step": 450
},
{
"epoch": 0.20444444444444446,
"grad_norm": 0.7793389558792114,
"learning_rate": 9.200000000000001e-05,
"loss": 1.8507,
"step": 460
},
{
"epoch": 0.2088888888888889,
"grad_norm": 0.5682786703109741,
"learning_rate": 9.4e-05,
"loss": 1.6696,
"step": 470
},
{
"epoch": 0.21333333333333335,
"grad_norm": 0.6214142441749573,
"learning_rate": 9.6e-05,
"loss": 1.7636,
"step": 480
},
{
"epoch": 0.21777777777777776,
"grad_norm": 0.6407720446586609,
"learning_rate": 9.8e-05,
"loss": 1.945,
"step": 490
},
{
"epoch": 0.2222222222222222,
"grad_norm": 0.5883258581161499,
"learning_rate": 0.0001,
"loss": 1.749,
"step": 500
},
{
"epoch": 0.22666666666666666,
"grad_norm": 0.7052844762802124,
"learning_rate": 9.942857142857144e-05,
"loss": 1.7102,
"step": 510
},
{
"epoch": 0.2311111111111111,
"grad_norm": 0.5479081869125366,
"learning_rate": 9.885714285714286e-05,
"loss": 1.7169,
"step": 520
},
{
"epoch": 0.23555555555555555,
"grad_norm": 0.5972569584846497,
"learning_rate": 9.828571428571429e-05,
"loss": 1.7405,
"step": 530
},
{
"epoch": 0.24,
"grad_norm": 0.5114515423774719,
"learning_rate": 9.771428571428572e-05,
"loss": 1.9784,
"step": 540
},
{
"epoch": 0.24444444444444444,
"grad_norm": 0.5898337960243225,
"learning_rate": 9.714285714285715e-05,
"loss": 1.7976,
"step": 550
},
{
"epoch": 0.24888888888888888,
"grad_norm": 0.6429341435432434,
"learning_rate": 9.657142857142858e-05,
"loss": 1.958,
"step": 560
},
{
"epoch": 0.25333333333333335,
"grad_norm": 0.46451956033706665,
"learning_rate": 9.6e-05,
"loss": 1.5966,
"step": 570
},
{
"epoch": 0.2577777777777778,
"grad_norm": 0.506208598613739,
"learning_rate": 9.542857142857143e-05,
"loss": 1.6479,
"step": 580
},
{
"epoch": 0.26222222222222225,
"grad_norm": 0.5113669633865356,
"learning_rate": 9.485714285714287e-05,
"loss": 1.6449,
"step": 590
},
{
"epoch": 0.26666666666666666,
"grad_norm": 0.5901801586151123,
"learning_rate": 9.428571428571429e-05,
"loss": 1.7377,
"step": 600
},
{
"epoch": 0.27111111111111114,
"grad_norm": 0.5738946199417114,
"learning_rate": 9.371428571428572e-05,
"loss": 1.8211,
"step": 610
},
{
"epoch": 0.27555555555555555,
"grad_norm": 0.5505834817886353,
"learning_rate": 9.314285714285715e-05,
"loss": 1.7923,
"step": 620
},
{
"epoch": 0.28,
"grad_norm": 0.6749151349067688,
"learning_rate": 9.257142857142858e-05,
"loss": 1.851,
"step": 630
},
{
"epoch": 0.28444444444444444,
"grad_norm": 0.618687629699707,
"learning_rate": 9.200000000000001e-05,
"loss": 1.8906,
"step": 640
},
{
"epoch": 0.28888888888888886,
"grad_norm": 0.592284619808197,
"learning_rate": 9.142857142857143e-05,
"loss": 1.8052,
"step": 650
},
{
"epoch": 0.29333333333333333,
"grad_norm": 0.6234279274940491,
"learning_rate": 9.085714285714286e-05,
"loss": 1.7278,
"step": 660
},
{
"epoch": 0.29777777777777775,
"grad_norm": 0.5879189372062683,
"learning_rate": 9.028571428571428e-05,
"loss": 1.8085,
"step": 670
},
{
"epoch": 0.3022222222222222,
"grad_norm": 0.6300005912780762,
"learning_rate": 8.971428571428571e-05,
"loss": 1.7155,
"step": 680
},
{
"epoch": 0.30666666666666664,
"grad_norm": 0.563451886177063,
"learning_rate": 8.914285714285715e-05,
"loss": 1.7602,
"step": 690
},
{
"epoch": 0.3111111111111111,
"grad_norm": 0.6689388751983643,
"learning_rate": 8.857142857142857e-05,
"loss": 1.7183,
"step": 700
},
{
"epoch": 0.31555555555555553,
"grad_norm": 0.5935807228088379,
"learning_rate": 8.800000000000001e-05,
"loss": 1.8198,
"step": 710
},
{
"epoch": 0.32,
"grad_norm": 0.6254555583000183,
"learning_rate": 8.742857142857144e-05,
"loss": 1.7565,
"step": 720
},
{
"epoch": 0.3244444444444444,
"grad_norm": 0.640834391117096,
"learning_rate": 8.685714285714286e-05,
"loss": 1.6407,
"step": 730
},
{
"epoch": 0.3288888888888889,
"grad_norm": 0.7603657245635986,
"learning_rate": 8.62857142857143e-05,
"loss": 1.8392,
"step": 740
},
{
"epoch": 0.3333333333333333,
"grad_norm": 0.5401626229286194,
"learning_rate": 8.571428571428571e-05,
"loss": 1.4939,
"step": 750
},
{
"epoch": 0.3377777777777778,
"grad_norm": 0.5616275668144226,
"learning_rate": 8.514285714285714e-05,
"loss": 1.6581,
"step": 760
},
{
"epoch": 0.3422222222222222,
"grad_norm": 0.6039714813232422,
"learning_rate": 8.457142857142858e-05,
"loss": 1.7711,
"step": 770
},
{
"epoch": 0.3466666666666667,
"grad_norm": 0.6184443831443787,
"learning_rate": 8.4e-05,
"loss": 1.709,
"step": 780
},
{
"epoch": 0.3511111111111111,
"grad_norm": 0.5194800496101379,
"learning_rate": 8.342857142857143e-05,
"loss": 1.7707,
"step": 790
},
{
"epoch": 0.35555555555555557,
"grad_norm": 0.6379169225692749,
"learning_rate": 8.285714285714287e-05,
"loss": 1.8612,
"step": 800
},
{
"epoch": 0.36,
"grad_norm": 0.6198997497558594,
"learning_rate": 8.228571428571429e-05,
"loss": 1.8448,
"step": 810
},
{
"epoch": 0.36444444444444446,
"grad_norm": 0.6147898435592651,
"learning_rate": 8.171428571428572e-05,
"loss": 1.6975,
"step": 820
},
{
"epoch": 0.3688888888888889,
"grad_norm": 0.5424386858940125,
"learning_rate": 8.114285714285714e-05,
"loss": 1.6583,
"step": 830
},
{
"epoch": 0.37333333333333335,
"grad_norm": 0.607720673084259,
"learning_rate": 8.057142857142857e-05,
"loss": 1.6709,
"step": 840
},
{
"epoch": 0.37777777777777777,
"grad_norm": 0.5133110880851746,
"learning_rate": 8e-05,
"loss": 1.7619,
"step": 850
},
{
"epoch": 0.38222222222222224,
"grad_norm": 0.525132417678833,
"learning_rate": 7.942857142857143e-05,
"loss": 1.651,
"step": 860
},
{
"epoch": 0.38666666666666666,
"grad_norm": 0.4882131516933441,
"learning_rate": 7.885714285714286e-05,
"loss": 1.6483,
"step": 870
},
{
"epoch": 0.39111111111111113,
"grad_norm": 0.6584396958351135,
"learning_rate": 7.828571428571429e-05,
"loss": 1.7908,
"step": 880
},
{
"epoch": 0.39555555555555555,
"grad_norm": 0.4846736490726471,
"learning_rate": 7.771428571428572e-05,
"loss": 1.7241,
"step": 890
},
{
"epoch": 0.4,
"grad_norm": 0.5569609999656677,
"learning_rate": 7.714285714285715e-05,
"loss": 1.8487,
"step": 900
},
{
"epoch": 0.40444444444444444,
"grad_norm": 0.47317251563072205,
"learning_rate": 7.657142857142857e-05,
"loss": 1.5844,
"step": 910
},
{
"epoch": 0.4088888888888889,
"grad_norm": 0.49643898010253906,
"learning_rate": 7.6e-05,
"loss": 1.701,
"step": 920
},
{
"epoch": 0.41333333333333333,
"grad_norm": 0.6150220036506653,
"learning_rate": 7.542857142857144e-05,
"loss": 1.6521,
"step": 930
},
{
"epoch": 0.4177777777777778,
"grad_norm": 0.5863474607467651,
"learning_rate": 7.485714285714285e-05,
"loss": 1.7961,
"step": 940
},
{
"epoch": 0.4222222222222222,
"grad_norm": 0.46018537878990173,
"learning_rate": 7.428571428571429e-05,
"loss": 1.5727,
"step": 950
},
{
"epoch": 0.4266666666666667,
"grad_norm": 0.5820701718330383,
"learning_rate": 7.371428571428572e-05,
"loss": 1.7221,
"step": 960
},
{
"epoch": 0.4311111111111111,
"grad_norm": 0.5305566787719727,
"learning_rate": 7.314285714285715e-05,
"loss": 1.5491,
"step": 970
},
{
"epoch": 0.43555555555555553,
"grad_norm": 0.44739487767219543,
"learning_rate": 7.257142857142858e-05,
"loss": 1.7449,
"step": 980
},
{
"epoch": 0.44,
"grad_norm": 0.525854766368866,
"learning_rate": 7.2e-05,
"loss": 1.6216,
"step": 990
},
{
"epoch": 0.4444444444444444,
"grad_norm": 0.6370983719825745,
"learning_rate": 7.142857142857143e-05,
"loss": 1.8326,
"step": 1000
},
{
"epoch": 0.4488888888888889,
"grad_norm": 0.5000634789466858,
"learning_rate": 7.085714285714285e-05,
"loss": 1.6554,
"step": 1010
},
{
"epoch": 0.4533333333333333,
"grad_norm": 0.5493870973587036,
"learning_rate": 7.028571428571428e-05,
"loss": 1.6535,
"step": 1020
},
{
"epoch": 0.4577777777777778,
"grad_norm": 0.6068606376647949,
"learning_rate": 6.971428571428572e-05,
"loss": 1.7912,
"step": 1030
},
{
"epoch": 0.4622222222222222,
"grad_norm": 0.36175239086151123,
"learning_rate": 6.914285714285715e-05,
"loss": 1.7161,
"step": 1040
},
{
"epoch": 0.4666666666666667,
"grad_norm": 0.4946162700653076,
"learning_rate": 6.857142857142858e-05,
"loss": 1.7134,
"step": 1050
},
{
"epoch": 0.4711111111111111,
"grad_norm": 0.570744514465332,
"learning_rate": 6.800000000000001e-05,
"loss": 1.7526,
"step": 1060
},
{
"epoch": 0.47555555555555556,
"grad_norm": 0.4829612374305725,
"learning_rate": 6.742857142857143e-05,
"loss": 1.5849,
"step": 1070
},
{
"epoch": 0.48,
"grad_norm": 0.5220139026641846,
"learning_rate": 6.685714285714286e-05,
"loss": 1.5798,
"step": 1080
},
{
"epoch": 0.48444444444444446,
"grad_norm": 0.4307192265987396,
"learning_rate": 6.628571428571428e-05,
"loss": 1.6771,
"step": 1090
},
{
"epoch": 0.4888888888888889,
"grad_norm": 0.5403544306755066,
"learning_rate": 6.571428571428571e-05,
"loss": 1.6165,
"step": 1100
},
{
"epoch": 0.49333333333333335,
"grad_norm": 0.47385355830192566,
"learning_rate": 6.514285714285715e-05,
"loss": 1.6693,
"step": 1110
},
{
"epoch": 0.49777777777777776,
"grad_norm": 0.5639126300811768,
"learning_rate": 6.457142857142856e-05,
"loss": 1.6192,
"step": 1120
},
{
"epoch": 0.5022222222222222,
"grad_norm": 0.596899688243866,
"learning_rate": 6.400000000000001e-05,
"loss": 1.742,
"step": 1130
},
{
"epoch": 0.5066666666666667,
"grad_norm": 0.5001611113548279,
"learning_rate": 6.342857142857143e-05,
"loss": 1.7284,
"step": 1140
},
{
"epoch": 0.5111111111111111,
"grad_norm": 0.5272433757781982,
"learning_rate": 6.285714285714286e-05,
"loss": 1.7103,
"step": 1150
},
{
"epoch": 0.5155555555555555,
"grad_norm": 0.46714940667152405,
"learning_rate": 6.22857142857143e-05,
"loss": 1.739,
"step": 1160
},
{
"epoch": 0.52,
"grad_norm": 0.4891936182975769,
"learning_rate": 6.171428571428571e-05,
"loss": 1.5622,
"step": 1170
},
{
"epoch": 0.5244444444444445,
"grad_norm": 0.5693128705024719,
"learning_rate": 6.114285714285714e-05,
"loss": 1.7711,
"step": 1180
},
{
"epoch": 0.5288888888888889,
"grad_norm": 0.4832131862640381,
"learning_rate": 6.0571428571428576e-05,
"loss": 1.6518,
"step": 1190
},
{
"epoch": 0.5333333333333333,
"grad_norm": 0.4521544277667999,
"learning_rate": 6e-05,
"loss": 1.7293,
"step": 1200
},
{
"epoch": 0.5377777777777778,
"grad_norm": 0.530257523059845,
"learning_rate": 5.9428571428571434e-05,
"loss": 1.7398,
"step": 1210
},
{
"epoch": 0.5422222222222223,
"grad_norm": 0.4766942262649536,
"learning_rate": 5.885714285714285e-05,
"loss": 1.5728,
"step": 1220
},
{
"epoch": 0.5466666666666666,
"grad_norm": 0.5979341864585876,
"learning_rate": 5.828571428571429e-05,
"loss": 1.7144,
"step": 1230
},
{
"epoch": 0.5511111111111111,
"grad_norm": 0.48419347405433655,
"learning_rate": 5.771428571428572e-05,
"loss": 1.6109,
"step": 1240
},
{
"epoch": 0.5555555555555556,
"grad_norm": 0.5022163391113281,
"learning_rate": 5.714285714285714e-05,
"loss": 1.6527,
"step": 1250
},
{
"epoch": 0.56,
"grad_norm": 0.44246387481689453,
"learning_rate": 5.6571428571428574e-05,
"loss": 1.5973,
"step": 1260
},
{
"epoch": 0.5644444444444444,
"grad_norm": 0.4790962338447571,
"learning_rate": 5.6000000000000006e-05,
"loss": 1.7611,
"step": 1270
},
{
"epoch": 0.5688888888888889,
"grad_norm": 0.539997398853302,
"learning_rate": 5.542857142857143e-05,
"loss": 1.6742,
"step": 1280
},
{
"epoch": 0.5733333333333334,
"grad_norm": 0.4964543282985687,
"learning_rate": 5.485714285714286e-05,
"loss": 1.7395,
"step": 1290
},
{
"epoch": 0.5777777777777777,
"grad_norm": 0.5202584266662598,
"learning_rate": 5.428571428571428e-05,
"loss": 1.8882,
"step": 1300
},
{
"epoch": 0.5822222222222222,
"grad_norm": 0.5655657649040222,
"learning_rate": 5.3714285714285714e-05,
"loss": 1.6829,
"step": 1310
},
{
"epoch": 0.5866666666666667,
"grad_norm": 0.4495587944984436,
"learning_rate": 5.314285714285715e-05,
"loss": 1.6082,
"step": 1320
},
{
"epoch": 0.5911111111111111,
"grad_norm": 0.5401484370231628,
"learning_rate": 5.257142857142857e-05,
"loss": 1.6704,
"step": 1330
},
{
"epoch": 0.5955555555555555,
"grad_norm": 0.6409158706665039,
"learning_rate": 5.2000000000000004e-05,
"loss": 1.6984,
"step": 1340
},
{
"epoch": 0.6,
"grad_norm": 0.47010332345962524,
"learning_rate": 5.142857142857143e-05,
"loss": 1.7012,
"step": 1350
},
{
"epoch": 0.6044444444444445,
"grad_norm": 0.5039106011390686,
"learning_rate": 5.085714285714286e-05,
"loss": 1.7446,
"step": 1360
},
{
"epoch": 0.6088888888888889,
"grad_norm": 0.46006426215171814,
"learning_rate": 5.028571428571429e-05,
"loss": 1.4179,
"step": 1370
},
{
"epoch": 0.6133333333333333,
"grad_norm": 0.5222061276435852,
"learning_rate": 4.971428571428572e-05,
"loss": 1.6808,
"step": 1380
},
{
"epoch": 0.6177777777777778,
"grad_norm": 0.45127660036087036,
"learning_rate": 4.9142857142857144e-05,
"loss": 1.653,
"step": 1390
},
{
"epoch": 0.6222222222222222,
"grad_norm": 0.4859090745449066,
"learning_rate": 4.8571428571428576e-05,
"loss": 1.7781,
"step": 1400
},
{
"epoch": 0.6266666666666667,
"grad_norm": 0.6080654859542847,
"learning_rate": 4.8e-05,
"loss": 1.6916,
"step": 1410
},
{
"epoch": 0.6311111111111111,
"grad_norm": 0.5803218483924866,
"learning_rate": 4.742857142857143e-05,
"loss": 1.7859,
"step": 1420
},
{
"epoch": 0.6355555555555555,
"grad_norm": 0.590130090713501,
"learning_rate": 4.685714285714286e-05,
"loss": 1.6935,
"step": 1430
},
{
"epoch": 0.64,
"grad_norm": 0.4160462021827698,
"learning_rate": 4.628571428571429e-05,
"loss": 1.5872,
"step": 1440
},
{
"epoch": 0.6444444444444445,
"grad_norm": 0.4726947546005249,
"learning_rate": 4.5714285714285716e-05,
"loss": 1.7101,
"step": 1450
},
{
"epoch": 0.6488888888888888,
"grad_norm": 0.48443475365638733,
"learning_rate": 4.514285714285714e-05,
"loss": 1.7473,
"step": 1460
},
{
"epoch": 0.6533333333333333,
"grad_norm": 0.5587878823280334,
"learning_rate": 4.4571428571428574e-05,
"loss": 1.5633,
"step": 1470
},
{
"epoch": 0.6577777777777778,
"grad_norm": 0.43862953782081604,
"learning_rate": 4.4000000000000006e-05,
"loss": 1.6364,
"step": 1480
},
{
"epoch": 0.6622222222222223,
"grad_norm": 0.4286442995071411,
"learning_rate": 4.342857142857143e-05,
"loss": 1.6191,
"step": 1490
},
{
"epoch": 0.6666666666666666,
"grad_norm": 0.45126351714134216,
"learning_rate": 4.2857142857142856e-05,
"loss": 1.7249,
"step": 1500
},
{
"epoch": 0.6711111111111111,
"grad_norm": 0.5152072906494141,
"learning_rate": 4.228571428571429e-05,
"loss": 1.6294,
"step": 1510
},
{
"epoch": 0.6755555555555556,
"grad_norm": 0.4662505090236664,
"learning_rate": 4.1714285714285714e-05,
"loss": 1.6245,
"step": 1520
},
{
"epoch": 0.68,
"grad_norm": 0.49927669763565063,
"learning_rate": 4.1142857142857146e-05,
"loss": 1.5931,
"step": 1530
},
{
"epoch": 0.6844444444444444,
"grad_norm": 0.4711079001426697,
"learning_rate": 4.057142857142857e-05,
"loss": 1.6273,
"step": 1540
},
{
"epoch": 0.6888888888888889,
"grad_norm": 0.5319389700889587,
"learning_rate": 4e-05,
"loss": 1.7385,
"step": 1550
},
{
"epoch": 0.6933333333333334,
"grad_norm": 0.4717606008052826,
"learning_rate": 3.942857142857143e-05,
"loss": 1.7488,
"step": 1560
},
{
"epoch": 0.6977777777777778,
"grad_norm": 0.4487731158733368,
"learning_rate": 3.885714285714286e-05,
"loss": 1.4776,
"step": 1570
},
{
"epoch": 0.7022222222222222,
"grad_norm": 0.594499409198761,
"learning_rate": 3.8285714285714286e-05,
"loss": 1.5591,
"step": 1580
},
{
"epoch": 0.7066666666666667,
"grad_norm": 0.5072243809700012,
"learning_rate": 3.771428571428572e-05,
"loss": 1.6309,
"step": 1590
},
{
"epoch": 0.7111111111111111,
"grad_norm": 0.6944729685783386,
"learning_rate": 3.7142857142857143e-05,
"loss": 1.6328,
"step": 1600
},
{
"epoch": 0.7155555555555555,
"grad_norm": 0.41481533646583557,
"learning_rate": 3.6571428571428576e-05,
"loss": 1.541,
"step": 1610
},
{
"epoch": 0.72,
"grad_norm": 0.45629650354385376,
"learning_rate": 3.6e-05,
"loss": 1.7933,
"step": 1620
},
{
"epoch": 0.7244444444444444,
"grad_norm": 0.4524475932121277,
"learning_rate": 3.5428571428571426e-05,
"loss": 1.7052,
"step": 1630
},
{
"epoch": 0.7288888888888889,
"grad_norm": 0.5357774496078491,
"learning_rate": 3.485714285714286e-05,
"loss": 1.6476,
"step": 1640
},
{
"epoch": 0.7333333333333333,
"grad_norm": 0.4461857080459595,
"learning_rate": 3.428571428571429e-05,
"loss": 1.5601,
"step": 1650
},
{
"epoch": 0.7377777777777778,
"grad_norm": 0.5301758050918579,
"learning_rate": 3.3714285714285716e-05,
"loss": 1.8176,
"step": 1660
},
{
"epoch": 0.7422222222222222,
"grad_norm": 1.122097134590149,
"learning_rate": 3.314285714285714e-05,
"loss": 1.6481,
"step": 1670
},
{
"epoch": 0.7466666666666667,
"grad_norm": 0.6046774387359619,
"learning_rate": 3.257142857142857e-05,
"loss": 1.8148,
"step": 1680
},
{
"epoch": 0.7511111111111111,
"grad_norm": 0.4735705256462097,
"learning_rate": 3.2000000000000005e-05,
"loss": 1.5967,
"step": 1690
},
{
"epoch": 0.7555555555555555,
"grad_norm": 0.4766364097595215,
"learning_rate": 3.142857142857143e-05,
"loss": 1.6152,
"step": 1700
},
{
"epoch": 0.76,
"grad_norm": 0.5077019333839417,
"learning_rate": 3.0857142857142856e-05,
"loss": 1.6901,
"step": 1710
},
{
"epoch": 0.7644444444444445,
"grad_norm": 0.47451454401016235,
"learning_rate": 3.0285714285714288e-05,
"loss": 1.5958,
"step": 1720
},
{
"epoch": 0.7688888888888888,
"grad_norm": 0.4522535800933838,
"learning_rate": 2.9714285714285717e-05,
"loss": 1.5278,
"step": 1730
},
{
"epoch": 0.7733333333333333,
"grad_norm": 0.47677576541900635,
"learning_rate": 2.9142857142857146e-05,
"loss": 1.7089,
"step": 1740
},
{
"epoch": 0.7777777777777778,
"grad_norm": 0.5438882112503052,
"learning_rate": 2.857142857142857e-05,
"loss": 1.6967,
"step": 1750
},
{
"epoch": 0.7822222222222223,
"grad_norm": 0.5106326341629028,
"learning_rate": 2.8000000000000003e-05,
"loss": 1.6133,
"step": 1760
},
{
"epoch": 0.7866666666666666,
"grad_norm": 0.48920413851737976,
"learning_rate": 2.742857142857143e-05,
"loss": 1.5464,
"step": 1770
},
{
"epoch": 0.7911111111111111,
"grad_norm": 0.4835570156574249,
"learning_rate": 2.6857142857142857e-05,
"loss": 1.6191,
"step": 1780
},
{
"epoch": 0.7955555555555556,
"grad_norm": 0.4348030686378479,
"learning_rate": 2.6285714285714286e-05,
"loss": 1.595,
"step": 1790
},
{
"epoch": 0.8,
"grad_norm": 0.5459887981414795,
"learning_rate": 2.5714285714285714e-05,
"loss": 1.6642,
"step": 1800
},
{
"epoch": 0.8044444444444444,
"grad_norm": 0.49609118700027466,
"learning_rate": 2.5142857142857147e-05,
"loss": 1.6884,
"step": 1810
},
{
"epoch": 0.8088888888888889,
"grad_norm": 0.49508237838745117,
"learning_rate": 2.4571428571428572e-05,
"loss": 1.5543,
"step": 1820
},
{
"epoch": 0.8133333333333334,
"grad_norm": 0.5876829624176025,
"learning_rate": 2.4e-05,
"loss": 1.5876,
"step": 1830
},
{
"epoch": 0.8177777777777778,
"grad_norm": 0.5161216259002686,
"learning_rate": 2.342857142857143e-05,
"loss": 1.5489,
"step": 1840
},
{
"epoch": 0.8222222222222222,
"grad_norm": 0.49379730224609375,
"learning_rate": 2.2857142857142858e-05,
"loss": 1.5353,
"step": 1850
},
{
"epoch": 0.8266666666666667,
"grad_norm": 0.4468284249305725,
"learning_rate": 2.2285714285714287e-05,
"loss": 1.5983,
"step": 1860
},
{
"epoch": 0.8311111111111111,
"grad_norm": 0.3884105384349823,
"learning_rate": 2.1714285714285715e-05,
"loss": 1.6029,
"step": 1870
},
{
"epoch": 0.8355555555555556,
"grad_norm": 0.5299472808837891,
"learning_rate": 2.1142857142857144e-05,
"loss": 1.4086,
"step": 1880
},
{
"epoch": 0.84,
"grad_norm": 0.4671512544155121,
"learning_rate": 2.0571428571428573e-05,
"loss": 1.6286,
"step": 1890
},
{
"epoch": 0.8444444444444444,
"grad_norm": 0.42520585656166077,
"learning_rate": 2e-05,
"loss": 1.5687,
"step": 1900
},
{
"epoch": 0.8488888888888889,
"grad_norm": 0.4671627879142761,
"learning_rate": 1.942857142857143e-05,
"loss": 1.7934,
"step": 1910
},
{
"epoch": 0.8533333333333334,
"grad_norm": 0.44849321246147156,
"learning_rate": 1.885714285714286e-05,
"loss": 1.4699,
"step": 1920
},
{
"epoch": 0.8577777777777778,
"grad_norm": 0.4914058744907379,
"learning_rate": 1.8285714285714288e-05,
"loss": 1.6696,
"step": 1930
},
{
"epoch": 0.8622222222222222,
"grad_norm": 0.4552600681781769,
"learning_rate": 1.7714285714285713e-05,
"loss": 1.5428,
"step": 1940
},
{
"epoch": 0.8666666666666667,
"grad_norm": 0.568909764289856,
"learning_rate": 1.7142857142857145e-05,
"loss": 1.5826,
"step": 1950
},
{
"epoch": 0.8711111111111111,
"grad_norm": 0.4071631133556366,
"learning_rate": 1.657142857142857e-05,
"loss": 1.4793,
"step": 1960
},
{
"epoch": 0.8755555555555555,
"grad_norm": 0.4576158821582794,
"learning_rate": 1.6000000000000003e-05,
"loss": 1.7766,
"step": 1970
},
{
"epoch": 0.88,
"grad_norm": 0.48867034912109375,
"learning_rate": 1.5428571428571428e-05,
"loss": 1.5677,
"step": 1980
},
{
"epoch": 0.8844444444444445,
"grad_norm": 0.5315440893173218,
"learning_rate": 1.4857142857142858e-05,
"loss": 1.6422,
"step": 1990
},
{
"epoch": 0.8888888888888888,
"grad_norm": 0.5676016211509705,
"learning_rate": 1.4285714285714285e-05,
"loss": 1.669,
"step": 2000
},
{
"epoch": 0.8933333333333333,
"grad_norm": 0.4910498261451721,
"learning_rate": 1.3714285714285716e-05,
"loss": 1.6654,
"step": 2010
},
{
"epoch": 0.8977777777777778,
"grad_norm": 0.4945501387119293,
"learning_rate": 1.3142857142857143e-05,
"loss": 1.752,
"step": 2020
},
{
"epoch": 0.9022222222222223,
"grad_norm": 0.4435444176197052,
"learning_rate": 1.2571428571428573e-05,
"loss": 1.4818,
"step": 2030
},
{
"epoch": 0.9066666666666666,
"grad_norm": 0.49968045949935913,
"learning_rate": 1.2e-05,
"loss": 1.7248,
"step": 2040
},
{
"epoch": 0.9111111111111111,
"grad_norm": 0.5078977942466736,
"learning_rate": 1.1428571428571429e-05,
"loss": 1.6665,
"step": 2050
},
{
"epoch": 0.9155555555555556,
"grad_norm": 0.4734516739845276,
"learning_rate": 1.0857142857142858e-05,
"loss": 1.6927,
"step": 2060
},
{
"epoch": 0.92,
"grad_norm": 0.5901415348052979,
"learning_rate": 1.0285714285714286e-05,
"loss": 1.575,
"step": 2070
},
{
"epoch": 0.9244444444444444,
"grad_norm": 0.4999895393848419,
"learning_rate": 9.714285714285715e-06,
"loss": 1.6373,
"step": 2080
},
{
"epoch": 0.9288888888888889,
"grad_norm": 0.5657374858856201,
"learning_rate": 9.142857142857144e-06,
"loss": 1.7343,
"step": 2090
},
{
"epoch": 0.9333333333333333,
"grad_norm": 0.4468814432621002,
"learning_rate": 8.571428571428573e-06,
"loss": 1.7404,
"step": 2100
},
{
"epoch": 0.9377777777777778,
"grad_norm": 0.4465270936489105,
"learning_rate": 8.000000000000001e-06,
"loss": 1.6573,
"step": 2110
},
{
"epoch": 0.9422222222222222,
"grad_norm": 0.573610782623291,
"learning_rate": 7.428571428571429e-06,
"loss": 1.6556,
"step": 2120
},
{
"epoch": 0.9466666666666667,
"grad_norm": 0.4416819214820862,
"learning_rate": 6.857142857142858e-06,
"loss": 1.6867,
"step": 2130
},
{
"epoch": 0.9511111111111111,
"grad_norm": 0.5595669150352478,
"learning_rate": 6.285714285714287e-06,
"loss": 1.6842,
"step": 2140
},
{
"epoch": 0.9555555555555556,
"grad_norm": 0.4565703868865967,
"learning_rate": 5.7142857142857145e-06,
"loss": 1.5335,
"step": 2150
},
{
"epoch": 0.96,
"grad_norm": 0.5595963001251221,
"learning_rate": 5.142857142857143e-06,
"loss": 1.7135,
"step": 2160
},
{
"epoch": 0.9644444444444444,
"grad_norm": 0.4642212986946106,
"learning_rate": 4.571428571428572e-06,
"loss": 1.6675,
"step": 2170
},
{
"epoch": 0.9688888888888889,
"grad_norm": 0.45244458317756653,
"learning_rate": 4.000000000000001e-06,
"loss": 1.573,
"step": 2180
},
{
"epoch": 0.9733333333333334,
"grad_norm": 0.4644954204559326,
"learning_rate": 3.428571428571429e-06,
"loss": 1.5292,
"step": 2190
},
{
"epoch": 0.9777777777777777,
"grad_norm": 0.4594193398952484,
"learning_rate": 2.8571428571428573e-06,
"loss": 1.6958,
"step": 2200
},
{
"epoch": 0.9822222222222222,
"grad_norm": 0.4561087489128113,
"learning_rate": 2.285714285714286e-06,
"loss": 1.6534,
"step": 2210
},
{
"epoch": 0.9866666666666667,
"grad_norm": 0.5011770129203796,
"learning_rate": 1.7142857142857145e-06,
"loss": 1.4897,
"step": 2220
},
{
"epoch": 0.9911111111111112,
"grad_norm": 0.4924561083316803,
"learning_rate": 1.142857142857143e-06,
"loss": 1.7416,
"step": 2230
},
{
"epoch": 0.9955555555555555,
"grad_norm": 0.5766103863716125,
"learning_rate": 5.714285714285715e-07,
"loss": 1.727,
"step": 2240
},
{
"epoch": 1.0,
"grad_norm": 0.5178750157356262,
"learning_rate": 0.0,
"loss": 1.5411,
"step": 2250
}
],
"logging_steps": 10,
"max_steps": 2250,
"num_input_tokens_seen": 0,
"num_train_epochs": 1,
"save_steps": 5000,
"stateful_callbacks": {
"TrainerControl": {
"args": {
"should_epoch_stop": false,
"should_evaluate": false,
"should_log": false,
"should_save": true,
"should_training_stop": true
},
"attributes": {}
}
},
"total_flos": 8.8552192868352e+16,
"train_batch_size": 4,
"trial_name": null,
"trial_params": null
}